INDEX

Explanations

expressions indicating satisfactory performance or functioning

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

peri

-0.19

/Foundation

-0.16

newInstance

-0.15

ÙĪÙĦÛĮ

-0.15

/Branch

-0.15

ari

-0.15

éĳĳ

-0.14

ensex

-0.14

ãĥªãĥ¼ãĤº

-0.13

 sink

-0.13

POSITIVE LOGITS

ipa

0.17

 Mund

0.15

à¤Ĥà¤ļ

0.15

asel

0.15

(er

0.14

/sys

0.14

 giden

0.14

iola

0.14

ushman

0.14

åħĪ

0.14

Activations Density 0.026%

expressions indicating satisfactory performance or functioning

No Comments

No Known Activations